Pinned Repositories
act-tensorflow
Adaptive Computation Time algorithm in Tensorflow
action-recognition-visual-attention
Action recognition using soft attention based deep recurrent neural networks
arctic-captions
async-rl
Replicating "Asynchronous Methods for Deep Reinforcement Learning" (http://arxiv.org/abs/1602.01783)
async-rl-1
Tensorflow + Keras + OpenAI Gym implementation of 1-step Q Learning from "Asynchronous Methods for Deep Reinforcement Learning"
async_deep_reinforce
Asynchronous Methods for Deep Reinforcement Learning
DeeperINP
In this repository, we implement Bayesian NN following Gal's method, also incorporate implementations of deeper NNs (Hightway NN, RHN, ResNet, GridLSTM) in player simulation modeling and DRL in interactive narrative personalization.
Pengcheng-Wang's Repositories
Pengcheng-Wang/DeeperINP
In this repository, we implement Bayesian NN following Gal's method, also incorporate implementations of deeper NNs (Hightway NN, RHN, ResNet, GridLSTM) in player simulation modeling and DRL in interactive narrative personalization.
Pengcheng-Wang/act-tensorflow
Adaptive Computation Time algorithm in Tensorflow
Pengcheng-Wang/action-recognition-visual-attention
Action recognition using soft attention based deep recurrent neural networks
Pengcheng-Wang/async_deep_reinforce
Asynchronous Methods for Deep Reinforcement Learning
Pengcheng-Wang/Atari
Persistent advantage learning dueling double DQN for the Arcade Learning Environment
Pengcheng-Wang/Attention-OCR
Visual Attention based OCR
Pengcheng-Wang/bayareadlschool
Slides and exercises for the Theano tutorial at the Deep Learning School in Stanford, September 24-25, 2016
Pengcheng-Wang/BayesianRNN
Code for the paper "A Theoretically Grounded Application of Dropout in Recurrent Neural Networks"
Pengcheng-Wang/burlap
Repository for the ongoing development of the Brown-UMBC Reinforcement Learning And Planning (BURLAP) java library
Pengcheng-Wang/char-rnn
Multi-layer Recurrent Neural Networks (LSTM, GRU, RNN) for character-level language models in Torch
Pengcheng-Wang/chatbot-retrieval
Dual LSTM Encoder for Dialog Response Generation
Pengcheng-Wang/DeepINP_2017
Interactive Narrative Planning with DRL
Pengcheng-Wang/DeepMind-Atari-Deep-Q-Learner
The original code from the DeepMind article + my tweaks
Pengcheng-Wang/draw
TensorFlow Implementation of "DRAW: A Recurrent Neural Network For Image Generation"
Pengcheng-Wang/fairseq
Facebook AI Research Sequence-to-Sequence Toolkit
Pengcheng-Wang/fb.resnet.torch
Torch implementation of ResNet from http://arxiv.org/abs/1512.03385 and training scripts
Pengcheng-Wang/grid-lstm
Torch7 implementation of Grid LSTM as described here: http://arxiv.org/pdf/1507.01526v2.pdf
Pengcheng-Wang/HelloWorld
Following the github tutorial
Pengcheng-Wang/icml2016-minecraft
Implementation of "Control of Memory, Active Perception, and Action in Minecraft"
Pengcheng-Wang/IntelliMediaCore
Collection of C# design patterns (MVVM, Repository, Promise, Singleton) and utility classes. The class library is intended to be used in conjunction with Unity 3D game engine projects or Mono-based servers and tools.
Pengcheng-Wang/keras_npi
NPI(Neural Programmer-Interpreters) implementation with Keras
Pengcheng-Wang/knowledge_distillation
Pengcheng-Wang/nn
Pengcheng-Wang/PlayWithRL
A Personal Tutorial Project about RL
Pengcheng-Wang/pytorch-a2c-ppo-acktr
PyTorch implementation of Advantage Actor Critic (A2C), Proximal Policy Optimization (PPO) and Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation (ACKTR).
Pengcheng-Wang/pytorch-value-iteration-networks
Pytorch implementation of Value Iteration Networks (NIPS 2016 best paper)
Pengcheng-Wang/RecurrentHighwayNetworks
Recurrent Highway Networks - Implementations for Tensorflow, Torch7, Theano and Brainstorm
Pengcheng-Wang/rlenvs
Reinforcement learning environments for Torch7
Pengcheng-Wang/rnn
Recurrent Neural Network library for Torch7's nn
Pengcheng-Wang/seq2seq-attn
Sequence-to-sequence model with LSTM encoder/decoders and attention